© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94229
    Prev
    Next
    INDEX
    Explanations

    length or duration of periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Fotografía
    -0.93
    Masukkan
    -0.85
    Compartir
    -0.82
    Altro
    -0.77
    жит
    -0.76
     acquistare
    -0.75
    elaar
    -0.75
    𝑹
    -0.74
    的一切
    -0.74
     altro
    -0.74
    POSITIVE LOGITS
     duration
    1.41
     gestation
    1.08
     tenure
    1.03
     exposure
    1.02
     periods
    1.00
     stay
    1.00
     distances
    0.99
     lifespan
    0.98
    duration
    0.98
     distancia
    0.97
    Activations Density 0.090%

    No Known Activations